Intelligent detection and tracking of the vessels on the sea play a
significant role in conducting traffic avoidance in unmanned surface
vessels(USV). Current traffic avoidance software relies mainly on Automated
Identification System (AIS) and radar to track other vessels to avoid
collisions and acts as a typical perception system to detect targets. However,
in a contested environment, emitting radar energy also presents the
vulnerability to detection by adversaries. Deactivating these Radiofrequency
transmitting sources will increase the threat of detection and degrade the
USV's ability to monitor shipping traffic in the vicinity. Therefore, an
intelligent visual perception system based on an onboard camera with passive
sensing capabilities that aims to assist USV in addressing this problem is
presented in this paper. This paper will present a novel low-cost vision
perception system for detecting and tracking vessels in the maritime
environment. This novel low-cost vision perception system is introduced using
the deep learning framework. A neural network, DisBeaNet, can detect vessels,
track, and estimate the vessel's distance and bearing from the monocular
camera. The outputs obtained from this neural network are used to determine the
latitude and longitude of the identified vessel.

本文介绍了一种智能视觉感知系统，基于机载摄像头的无人船舶中的智能检测和跟踪，用于在海上环境中检测和追踪船只。

DisBeaNet：深度神经网络提升无人水面器械的海上态势感知

DisBeaNet: A Deep Neural Network to augment Unmanned Surface Vessels for  maritime situational awareness

In many scenarios, especially biomedical applications, the correct
delineation of complex fine-scaled structures such as neurons, tissues, and
vessels is critical for downstream analysis. Despite the strong predictive
power of deep learning methods, they do not provide a satisfactory
representation of these structures, thus creating significant barriers in
scalable annotation and downstream analysis. In this dissertation, we tackle
such challenges by proposing novel representations of these topological
structures in a deep learning framework. We leverage the mathematical tools
from topological data analysis, i.e., persistent homology and discrete Morse
theory, to develop principled methods for better segmentation and uncertainty
estimation, which will become powerful tools for scalable annotation.

通过拓扑数据分析法，我们提出了一种新颖的深度学习框架，以更好地分割和不确定性评估复杂的细微结构，如生物医学应用中的神经元、组织和血管，为可扩展的标注提供了有力工具。

深度图像理解的拓扑表示学习

Learning Topological Representations for Deep Image Understanding

Although Digital Subtraction Angiography (DSA) is the most important imaging
for visualizing cerebrovascular anatomy, its interpretation by clinicians
remains difficult. This is particularly true when treating arteriovenous
malformations (AVMs), where entangled vasculature connecting arteries and veins
needs to be carefully identified.The presented method aims to enhance DSA image
series by highlighting critical information via automatic classification of
vessels using a combination of two learning models: An unsupervised machine
learning method based on Independent Component Analysis that decomposes the
phases of flow and a convolutional neural network that automatically delineates
the vessels in image space. The proposed method was tested on clinical DSA
images series and demonstrated efficient differentiation between arteries and
veins that provides a viable solution to enhance visualizations for clinical
use.

通过使用两种学习模型：基于独立成分分析的无监督机器学习方法和基于卷积神经网络的自动细分图像空间中的血管，提出的方法在 DSA 影像序列中通过突出关键信息进行自动分类血管来增强 DSA 图像序列，通过高效区分动脉和静脉为临床使用的可行解决方案。

数字减影血管造影中动静脉畸形的时空解缠

Spatiotemporal Disentanglement of Arteriovenous Malformations in Digital  Subtraction Angiography

Accurate segmentation of pulmonary airways and vessels is crucial for the
diagnosis and treatment of pulmonary diseases. However, current deep learning
approaches suffer from disconnectivity issues that hinder their clinical
usefulness. To address this challenge, we propose a post-processing approach
that leverages a data-driven method to repair the topology of disconnected
pulmonary tubular structures. Our approach formulates the problem as a keypoint
detection task, where a neural network is trained to predict keypoints that can
bridge disconnected components. We use a training data synthesis pipeline that
generates disconnected data from complete pulmonary structures. Moreover, the
new Pulmonary Tree Repairing (PTR) dataset is publicly available, which
comprises 800 complete 3D models of pulmonary airways, arteries, and veins, as
well as the synthetic disconnected data. Our code and data are available at
this https URL

提出一种基于深度学习的后处理方法，通过关键点检测任务修复肺部管状结构的连接性问题，解决当前深度学习方法在肺部病理诊断中的实用性问题。新的肺部树修复数据集（PTR）包括 800 个完整的三维肺部结构模型，可公开获取。